Digital Commons Network^™

On Minimizing Adversarial Counterfactual Error In Adversarial Reinforcement Learning, Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the information observed by the agent, the state becomes only partially observable. Existing approaches address this by either enforcing consistent actions across nearby states or maximizing the worst-case value within adversarially perturbed observations. However, the former suffers from performance degradation when attacks succeed, while the latter tends to be overly conservative, leading to suboptimal performance in benign settings. We hypothesize that these limitations stem from their failing to account for …

Predictive Modelling For Vessel Traffic Flow: A Comprehensive Survey From Statistics To Ai, Deshan. Chen, Chen. Huang, Tengze. Fan, Hoong Chuin Lau, Xinping. Yan

Research Collection School Of Computing and Information Systems

Recognizing the specific complexities of vessel traffic flow, this comprehensive survey exclusively addresses the predictive modelling in maritime transportation, tracing the evolution from conventional statistical approaches to modern artificial intelligence (AI) techniques. The survey examines a broad range of predictive targets, including vessel volume, trajectories, velocities, destinations and traffic patterns. Through bibliometric analysis utilizing Citespace, the central research themes and technological trends characterizing the vessel traffic flow prediction domain have been identified and discussed. Our analysis indicates a clear trend towards AI-based models, highlighting their increasing dominance in enhancing predictive accuracy and efficiency. Additionally, we highlight persistent challenges, such as …

Open-Set Graph Anomaly Detection Via Normal Structure Regularisation, Qizhou Wang, Guansong Pang, Mahsa Salehi, Xiaokun Xia, Christopher Leckie

Research Collection School Of Computing and Information Systems

This paper considers an important Graph Anomaly Detection (GAD) task, namely open-set GAD, which aims to train a detection model using a small number of normal and anomaly nodes (referred to as *seen anomalies*) to detect both seen anomalies and *unseen anomalies* (*i.e*., anomalies that cannot be illustrated the training anomalies). Those labelled training data provide crucial prior knowledge about abnormalities for GAD models, enabling substantially reduced detection errors. However, current supervised GAD methods tend to over-emphasise fitting the seen anomalies, leading to many errors of detecting the unseen anomalies as normal nodes. Further, existing open-set AD models were introduced …

A Functional Software Reference Architecture For Llm-Integrated Systems, Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo

Research Collection School Of Computing and Information Systems

The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution. However, the absence of a commonly accepted software reference architecture hinders systematic reasoning about their design and quality attributes. This gap makes it challenging to address critical concerns like privacy, security, modularity, and interoperability, which are increasingly important as these systems grow in complexity and societal impact. In this paper, we describe our emerging results for a preliminary functional reference architecture as a conceptual framework to address these challenges and guide the design, evaluation, and evolution of large …

Prioritizing Speech Test Cases, Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi, Bowen Xu, Xin Zhou, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

As Automated Speech Recognition (ASR) systems gain widespread acceptance, there is a pressing need to rigorously test and enhance their performance. Nonetheless, the process of collecting and executing speech test cases is typically both costly and time-consuming. This presents a compelling case for the strategic prioritization of speech test cases, which consist of a piece of audio and the corresponding reference text. The central question we address is: In what sequence should speech test cases be collected and executed to identify the maximum number of errors at the earliest stage? In this study, we introduce PRiOritizing sPeecH tEsT …

Bigcodebench: Benchmarking Code Generation With Diverse Function Calls And Complex Instructions, T.Y. Zhuo, M.C. Vu, J. Chim, ..., David Lo

Research Collection School Of Computing and Information Systems

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately …

Scuzer: A Scheduling Optimization Fuzzer For Tvm, Xiangxiang Chen, Xingwei Lin, Jingyi Wang, Jun Sun, Jiashui Wang, Wenhai Wang

Research Collection School Of Computing and Information Systems

The concept of Deep Learning (DL) compiler was proposed to deploy DL models more efficiently on diverse hardware through optimization techniques. As one of the most popular DL compilers, TVM incorporates three levels (high-level, schedule, and low-level) of optimizations, which can inadvertently introduce code logic bugs and build failure bugs. Among these optimizations, scheduling optimization is the core component of DL compilers, which ensures the acceleration of models on all devices. However, the existing works only focus on the testing of high-level and low-level optimizations in TVM, fail to take the most important and challenging intermediate scheduling optimization layer into …

Constructive Trusts In Malaysia: A Methodological Reappraisal, Hang Wu Tang, Ying Khai Liew

Research Collection Yong Pung How School Of Law

In recent times, Malaysian courts have resorted to a ritual incantation of unconscionability and the notion of a remedial constructive trust to justify a declaration of a constructive trust. This methodology is unhelpful for approaching constructive trusts and has led the law to develop in an unprincipled and unpredictable fashion. Our central thesis is that the key Malaysian decisions could have been decided on the basis of pre-existing legal principles upon which English and Commonwealth courts have declared a constructive trust. We argue that future courts ought to realign their methodology with the orthodox tradition of incremental development of the …

The Digitalization Of Insolvency Proceedings, Aurelio Gurrea-Martinez

Research Collection Yong Pung How School Of Law

Despite the international divergences existing in the design of insolvency law, there is a common feature of insolvency proceedings that, to a greater or lesser extent, is somehow universal: insolvency proceedings are generally costly and lengthy processes. For that reason, it is not surprising that a significant body of the literature on insolvency law deals with different mechanisms to make insolvency proceedings more efficient. This article examines how technology can contribute to that goal. To that end, it starts by reviewing how countries are deploying, or can deploy, technology in different aspects and stages of insolvency proceedings and how such …

Siac Rules 2025: A Critical Evaluation In The Indian Arbitration Context, Siyuan Chen, Chin Kye Joel Ko

Research Collection Yong Pung How School Of Law

No abstract provided.

Beyond Non-Recognition: U.S.–Taiwan Trade Agreements In Indo-Pacific Dynamics, Pasha L. Hsieh

Research Collection Yong Pung How School Of Law

At the core of U.S.-China tensions and the Indo-Pacific strategy, the evolving legal frameworks that govern U.S.-Taiwan relations present legal intricacies under American and international law. The Article provides the first comprehensive analysis of the groundbreaking U.S.-Taiwan Initiative on 21st-Century Trade, the only Congress-approved trade agreement during the Biden administration. It argues that within the space of non-recognition, the United States has accorded Taiwan diverse and incremental forms of legal recognition, which culminated in the Initiative and its Implementation Act. Through an interdisciplinary lens, the Article develops a theoretical framework that bridges recognition theories under international law and international relations. …

Nurture Asia-Ready Singaporeans To Tap Growing Opportunities In The Region [Interview With The Straits Times], Sandra Davie, Piyush Gupta

Oral History Collection

In an interview with The Straits Times, as chairman of Singapore Management University, DBS Bank chief executive Piyush Gupta said the university should aim to become the “quintessential Asian university”, emulating DBS, which he had turned into the “quintessential Asian bank” since he took over the helm in 2009.

Director Overseas Experience And Cross-Border Acquisitions: Evidence From China, Liu Chenxi, Mengyao Kang

Research Collection Lee Kong Chian School Of Business

This study investigates the impact of director overseas experience on firms’ cross-border acquisition decisions. We find that firms with directors who have overseas experience tend to engage in more cross-border acquisitions. This finding remains robust across various types of overseas experience. This correlation is unlikely to be influenced by omitted variable biases or driven by reverse causality, where firms deliberately employ directors with overseas experience before initiating cross-border acquisitions. Additionally, director overseas experience is associated with higher announcement returns and enhanced post-merger performance. Further analysis reveals that director overseas experience affects cross-border acquisition decisions primarily through the cultural inclusivity channel. …

The Regenerative Future Of Loyalty: A Guide For Green Loyalty Programs To Engage Eco-Consumers, Simon J.D. Schillebeeckx, Ryan Merrill

Research Collection Lee Kong Chian School Of Business

Loyalty programs are challenged to attract and retain consumers who increasingly value purpose-driven engagement and environmental impact alongside traditional rewards. With growing awareness of climate issues, many customers expect brands to integrate sustainability and eco-conscious actions into their loyalty offerings.
 71% of consumers believe loyalty programs should support sustainable practices, and this expectation is particularly strong among younger demographics like Gen Z and Millennials. As companies respond by integrating eco-conscious actions — like recycling incentives, carbon offsets, and donations to green causes — these efforts foster emotional loyalty, drive repeat purchases, and ensure long-term retention. Loyalty programs that align with …

Offline Safe Reinforcement Learning Using Trajectory Classification, Ze Gong, Akshat Kumar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints at each time step (derived from global cost constraints) and this can result in either overly conservative policies or violation of safety constraints. In this paper, we propose to learn a policy that generates desirable trajectories and avoids undesirable trajectories. To be specific, we first partition the pre-collected dataset of state-action trajectories into desirable and undesirable subsets. Intuitively, the desirable set contains high reward and …

Occlusion-Insensitive Talking Head Video Generation Via Facelet Compensation, Yuhui Deng, Yuqin Lu, Yangyang Xu, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

Talking head video generation involves animating a still face image using facial motion cues derived from a driving video to replicate target poses and expressions. Traditional methods often rely on the assumption that the relative positions of facial keypoints remain unchanged. However, this assumption fails when keypoints are occluded or when the head is in a profile pose, leading to inconsistencies in identity and blurring in certain facial regions. In this paper, we introduce Occlusion-Insensitive Talking Head Video Generation, a novel approach that eliminates the reliance on spatial correlation of keypoints and instead leverages semantic correlation. Our method transforms facial …

Adapting Knowledge Prompt Tuning For Enhanced Automated Program Repair, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning be-comes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, using three LLMs of different sizes and six diverse datasets across four programming languages. Prompt tuning rewrites …

Mimic: Ai And Ar-Enhanced Multi-Modal, Immersive, Relative Instruction Comprehension, Dhanuja Wanniarachchi, Archan Misra

Research Collection School Of Computing and Information Systems

We present a multimodal instruction comprehension framework, called MImIC, that utilizes visual sensing (including LIDAR and 2D RGB sensing) & AI spatial reasoning capabilities to support more seamless and immersive interaction between humans and AI-driven situated assistive agents. MImIC's key new capability is to support disambiguation of a wider set of relative spatial references that users naturally employ while issuing spatially-situated instructions. To support enhanced visual grounding via a combination of both fully-qualified and relative attribute references, MImIC uses (a) a fine-tuned transformer-based language translation DNN to accurately convert natural verbal commands into a structured set of machine understandable constraints …

Explainable Neural Networks With Guarantee: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

The Influence Of Digitization Degree On The Internationalization Performance Of Family Firms, Hao Zhang

Dissertations and Theses Collection (Open Access)

In the report of the 20th National Congress of the Communist Party of China, it was clearly stated that efforts should be made to accelerate the development of thedigital economy, deepen the integration of the digital economy with the real economy, and strive to build a digital industrial cluster with international competitiveness. This grand blueprint not only highlights China's high regard for the future development of the digital economy but also points out the direction for China's economictransformation and upgrading. Meanwhile, the "Overall Layout Plan for Digital ChinaConstruction" further elaborates on this strategy and sets the ambitious goal of basically …

A Study Of The Impact Of Brand Management Strategies On Brand Rejuvenation - Evidence Based On Chinese Baijiu Brands, Hao Chen

Dissertations and Theses Collection (Open Access)

In recent years, China Baijiu industry has faced the challenges of a shrinking consumer market, aging and the rise of young consumers, prompting Baijiu brands to seek new growth points, especially to attract younger groups. As a result, brand rejuvenation has become a key strategic objective for spirits companies. Given that brand extension and brand alliance are effective strategies for traditional brands to expand into new markets, this study develops a model to explore the impact of these two brand management strategies on Baijiu brand rejuvenation and analyses the mediating roles of brand image and brand awareness as well as …

Research On The Technology And Economy Of Intelligent Transformation Of Textile Enterprises, Hongxia Zhang

Dissertations and Theses Collection (Open Access)

The Chinese government has proposed to promote the high-end, intelligent and green development of manufacturing in the next step. The China Textile Industry Federation issued the “14th Five-Year Development Outline for the Textile Industry”, emphasizing accelerating the development of intelligent manufacturing system integrators in the textile field to achieve the transformation and upgrading of the industry. At present, the outstanding problems restricting the rapid development of intelligent manufacturing in China’s textile industry include: Imperfect evaluation indicators; The management system does not match; The reconstruction path is not clear.
This topic (1) constructs a big data policy co-word network through quantitative …

The Relationship Between Industry Regulation And The Quality Of Micro-Dramas, Shuoyu Yao

Dissertations and Theses Collection (Open Access)

This paper is a study on the micro-drama industry, exploring the reasons for a large number of low-quality micro-dramas. Specifically, there are two potential problems: (1) the industry value allocation model is unreasonable, so producing high-quality micro-dramas does not receive sufficient returns; (2) regulatory oversight of the industry is insufficient. To investigate this recent phenomenon and the underlying problems, we collected a dataset of 165 micro-dramas and use the newly introduced regulation on the micro-drama industry in June 2024 as a policy shock. The findings show that, before the new regulations were introduced, micro-dramas with higher quality in expression received …

Family Succession And Corporate Investment Policy, Weiting Lin

Dissertations and Theses Collection (Open Access)

Family firms play a significant role in economic and social development, making substantial contributions to wealth creation, employment generation, and the enhancement of social welfare. However, the development of family firms faces numerous challenges, among which intergenerational succession stands out as one of the most critical. The intergenerational succession of family firms is crucial for their long-term sustainable development. In China, since the reform and opening up, private enterprises have experienced rapid growth, with most family firms still under the control of their first-generation founders. These firms are now entering a critical period of succession. The unique political, business, and …

Entrepreneurial Spirit And Firm Performance: An Empirical Study Based On Data From The Star Market​, Zhige Zhang

Dissertations and Theses Collection (Open Access)

Entrepreneurial spirit, as a vital production factor in contemporary society, plays a leading and guiding role throughout the entire life cycle of a business. In particular, entrepreneurial innovation spirit, a key element of entrepreneurial spirit, is a pivotal engine of economic and societal progress. This paper adopts an empirical research approach to analyze the correlation between entrepreneurial innovation spirit and firm outcome, delving into the impact of entrepreneurial innovation spirit on a firm's operational efficiency, profitability, solvency, and development capabilities. The findings provide theoretical support and practical guidance for enterprise management, ultimately contributing to the creation of greater corporate value …

Building Skills Now For Asean’S Future, Shoeb Kagda

Asian Management Insights

Upskilling of workers is critical for building a more resilient workforce and future-proofing economic growth. Upskilling has become a buzzword for governments across the region as they gear up to boost economic growth and improve productivity. A confluence of factors such as digitalisation, automation, and artificial intelligence is heralding a new age where these elements have become powerful drivers of economic success. There is enormous potential for Southeast Asia, which is home to the third largest labour force in the world and has a relatively young population, to upskill its workers. Historically a region that has depended on low-skilled manufacturing …

Wingspan: Taking Digital Learning To New Heights, Adam Tatarynowicz, Wee-Kiat Lim, Mahima Rao-Kachroo

Asian Management Insights

How an internal learning platform became a market success. Launched in April 2018, the learning experience platform (LXP) Wingspan was the brainchild of Infosys Co-Founder and Chairman Nandan Nilekani. He had observed that several critical trends were reshaping the world economy. For instance, digital natives were increasingly expecting the learning environment at their workplace to be available 24/7. The late 2000s were also a time when Infosys’ corporate clients had just started on their digital transformation journey. Hence, capturing talent and market share was a strategic priority for the company. In contrast, the learning delivery landscape at Infosys then was …

Social Mobility: What We Haven’T Talked About, Jacinth Tan

Asian Management Insights

More balanced understanding may curb unintended negative outcomes. While social mobility provides opportunities for a better life and societal progress, it can also lead to significant challenges, including burnout from hypercompetitive environments, feelings of isolation due to cultural mismatches, and self-blame stemming from the myth of meritocracy. Strengthening social safety nets and providing supportive environments in educational institutions and workplaces can help mitigate the unintended psychological and social costs of mobility. A nuanced approach to social mobility that acknowledges external systemic and psychological barriers, and fosters inclusivity, is necessary to ensure upward mobility benefits society while lowering the risk of …

Research On The Influence Of The Quantity And Quality Of Young Talents On Regional Economic Development, Jinzhao Liu

Dissertations and Theses Collection (Open Access)

This study focuses on the critical impact of both the quantity and quality of young talent on regional, particularly urban, economic development in terms of pace and quality. The paper examines how educated and innovative youth serve as catalysts for economic progress, driving innovation and entrepreneurship in urban areas. Through an examination of economic growth theories and innovation-driven development models, the research employs a Cobb-Douglas production function for empirical analysis, revealing the significant positive influence of high-quality young populations on regional GDP growth.

Concurrently, case studies of Zhongguancun and Suzhou's textile industry demonstrate the transformative power of young talent in …

Designing Pull-Based Energy System Rules For Public Buildings: An Application Of Modularity, Lei Wang

Dissertations and Theses Collection (Open Access)

Building energy systems, particularly Heating, Ventilation, and Air Conditioning (HVAC) systems, play a pivotal role in global sustainability efforts. Yet, traditional centralized HVAC systems continue to face major challenges: high energy consumption, significant operational costs, and limited adaptability to dynamic energy demands. These inefficiencies are compounded by the difficulty of integrating renewable energy sources into outdated system designs. As a result, substantial energy waste persists, posing obstacles to cost-effective, environmentally sustainable building operations.

This dissertation proposes a modular, pull-based energy framework to address these critical challenges. By combining the principles of modularity theory with demand-driven energy distribution, the framework enables …